CN212541329U - Dual-redundancy computer equipment based on domestic Loongson platform - Google Patents
Dual-redundancy computer equipment based on domestic Loongson platform Download PDFInfo
- Publication number
- CN212541329U CN212541329U CN202021358740.XU CN202021358740U CN212541329U CN 212541329 U CN212541329 U CN 212541329U CN 202021358740 U CN202021358740 U CN 202021358740U CN 212541329 U CN212541329 U CN 212541329U
- Authority
- CN
- China
- Prior art keywords
- standby
- module
- main
- machine
- computer device
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Hardware Redundancy (AREA)
Abstract
The utility model discloses a dual-redundancy computer device based on a domestic Loongson platform, which comprises a main computer device and a standby computer device which are respectively marked as a main computer and a standby computer, a main-standby synchronous module, a main-standby switching module and a cabinet management module, wherein the main computer device and the standby computer device are arranged on the domestic Loongson platform; each computer device includes: a BMC module and a measurement and control CPU module; and the BMC module is provided with a CAN and GPIO communication interface. The utility model discloses utilize the method of dual redundancy hot backup to guarantee that equipment can long-time effectual normal operating, and provide healthy monitoring module, can greatly reduced because the platform collapse probability that equipment unstability leads to effectively provide reliable and stable operation platform for domestic godson module.
Description
Technical Field
The utility model belongs to consolidate the computer field, in particular to dual redundancy computer equipment based on domestic godson platform.
Background
The reliability is an important index for measuring the automation, and especially for a domestic computer applied to the field of severe environment resistance, the reliability index is very important. Because of the technological limitations of the domestic computer at the present stage, the reliability problem is one of the main problems faced by the domestic computer system, so that the research on how to improve the reliability of the domestic computer is a very important subject for the development of the domestic computer at present.
The traditional computer time system generally comprises a computer main module, an operating system and an application software system, and the traditional computer mainly solves the problem of system reliability by improving the reliability of single computer software and hardware. According to past experience, the reliability of the single-computer software and hardware is only improved, the requirement of the whole system on the reliability cannot be met, and particularly, the difficulty in improving the reliability of the independent and controllable domestic software and hardware is relatively high.
SUMMERY OF THE UTILITY MODEL
An object of the utility model is to provide a can improve the dual redundant computer equipment of computer system reliability to the not enough of above-mentioned prior art existence.
Realize the utility model discloses the technical solution of purpose does: a dual-redundancy computer device based on a domestic Loongson platform comprises a main computer device and a standby computer device which are respectively marked as a main computer and a standby computer and are deployed on the domestic Loongson platform, a main and standby synchronization module, a main and standby switching module and a cabinet management module; each computer device includes: a BMC module and a measurement and control CPU module; the BMC module is provided with a CAN and GPIO communication interface;
the BMC module is used for reading slot position information of the GPIO communication interface, identifying a host and a standby machine according to the information, controlling the corresponding measurement and control CPU module to be immediately powered on and started and perform self-checking on the host, and controlling the corresponding measurement and control CPU module to delay the powering on and started and perform self-checking on the standby machine; the BMC module is used for receiving the CPU self-checking information and controlling the CPU module to normally work when the CPU self-checking information is in a normal running state;
the main and standby synchronization module is used for synchronizing data and state information of the main machine and the standby machine in real time;
the main/standby switching module is used for monitoring heartbeat signals and switching command signals of the host and the standby machines in real time, switching the main/standby machines according to the heartbeat signals and the switching command signals, broadcasting a switching result to other modules, and reporting the switching result to the cabinet management module through a CAN communication interface of the BMC module;
and the cabinet management module is used for realizing communication between the host and the standby machine.
Further, the dual-redundancy computer device further comprises a monitoring module, which is used for enabling the dual-redundancy computer device to suspend working when receiving the fault warning signal, or switching the normal working mode of the dual-redundancy computer device into a single machine working mode when the main or standby computer has one computer device to work normally; the normal working mode is that the main machine and the standby machine work normally, and the single machine working mode is that the main machine or the standby machine which has a fault does not work;
and the fault warning signal is sent to the monitoring module through the RS232 serial port when the BMC module receives the CPU self-checking information that the running state is abnormal.
Furthermore, the dual redundant computer device further comprises a VGA and an ethernet communication interface, wherein the VGA is used for outputting the state of the computer device, and the ethernet interface is used for updating, upgrading and debugging the computer device.
Further, the status information includes: the ready state indicates whether the current running state of the computer equipment is normal or not, the high level indicates normal, and the low level indicates abnormal; the main/standby state indicates that the current computer equipment is used as a host or a standby computer, the main state is high level, and the standby state is low level; and resetting the board-to-board signal to indicate whether the current computer equipment is to reset and restart the other computer equipment when the other computer equipment fails.
Further, the method for switching between the main and standby devices by the main and standby switching module includes:
the heartbeat detection mechanism is as follows: the method comprises the steps that a host machine and a standby machine mutually monitor heartbeat signals of the other side, when the standby machine is in a ready state, a standby state and normal heartbeat signals, and the standby machine does not monitor the heartbeat signals of the host machine in a plurality of periods, and when the standby machine does not respond when sending an appointed command to the host machine, the standby machine sends a standby and standby switching request signal to a standby and standby switching module, the standby and standby switching module realizes the switching of the standby and standby machines, the main state of the current host machine is converted into the standby state, and the standby state of the current standby machine is converted into the main state;
a handover command mechanism: the host machine sends a main-standby switching command to the main-standby switching module, the main-standby switching module realizes the main-standby switching, the main state of the current host machine is converted into a standby state, and the standby state of the current standby machine is converted into the main state.
Further, the master/slave switching request signal/master/slave switching command is sent by a heartbeat signal.
Compared with the prior art, the utility model, it is showing the advantage and is: 1) the reliability of the system is improved by adopting a dual redundancy technology; the system adopts signal synchronous work when in operation, when one computer breaks down, the other computer can be switched in time to take over the work, so as to ensure the uninterrupted operation of the system; 2) a health monitoring module (BMC module) is provided, so that the probability of platform breakdown caused by equipment instability can be greatly reduced, and a stable and reliable operation platform is effectively provided for a domestic Loongson module; 3) the state of the other side can be monitored between the two computers, so that the health states of the computers become transparent to each other, and if a problem is found, the switching can be carried out in time, and unnecessary loss is avoided; 4) two computers deployed by the dual-redundancy computer are in a hot standby state, so that the data processing efficiency of the whole computer system can be improved in the process of simultaneous operation, and meanwhile, the data fault tolerance is ensured.
The present invention will be described in further detail with reference to the accompanying drawings.
Drawings
FIG. 1 is a diagram illustrating a dual redundant computer of a domestic Loongson platform according to an embodiment.
FIG. 2 is a flowchart illustrating initialization of dual redundant computers of the domestic Loongson platform according to an embodiment.
FIG. 3 is a flowchart illustrating the operation of a dual-redundancy computer of the domestic Loongson platform according to an embodiment.
FIG. 4 is a block diagram of a device BMC management board in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In an embodiment, with reference to fig. 1, a dual-redundancy computer device based on a home-made loongson platform is provided, where the device includes a main computer device and a standby computer device, which are respectively marked as a host and a standby, deployed on the home-made loongson platform, a main-standby synchronization module, a main-standby switching module, and a cabinet management module; each computer device includes: a BMC module and a measurement and control CPU module; the BMC module is provided with a CAN and GPIO communication interface;
the BMC module is used for reading slot position information of the GPIO communication interface, identifying a host and a standby machine according to the information, controlling the corresponding measurement and control CPU module to be immediately powered on and started and perform self-checking on the host, and controlling the corresponding measurement and control CPU module to delay the powering on and started and perform self-checking on the standby machine; the BMC module is used for receiving the CPU self-checking information and controlling the CPU module to normally work when the CPU self-checking information is in a normal running state;
here, the host and the backup are identified based on the slot information, and the identification is performed by using a hardware interface signal without involving software, for example, a string of binary digits may be specified to represent the host, and a string of binary digits may represent the backup, and the string may be specifically set by a user.
Here, the self-checking is also performed according to the hardware interface signal, and the self-checking rule can also be set by the user.
Here, the BMC module includes a voltage and temperature detection circuit for detecting whether the voltage and temperature of the measurement and control CPU module are normal. Preferably, the temperature detection circuit adopts MF11-10 k-10% plug-in thermistors.
Here, in conjunction with fig. 4, the BMC health management module is powered by independent DC 3.3V, and includes: i is2The system comprises a C bus, a dual-redundancy CAN bus, 4 paths of input/output (IO) interfaces for identifying host and standby slot numbers, 1 path of reset output signal interfaces, 1 path of serial ports, 1 path of heating control interfaces and 3 paths of voltage and temperature detection signal interfaces.
The main and standby synchronization module is used for synchronizing data and state information of the main machine and the standby machine in real time;
the main/standby switching module is used for monitoring heartbeat signals and switching command signals of the host and the standby machines in real time, switching the main/standby machines according to the heartbeat signals and the switching command signals, broadcasting a switching result to other modules, and reporting the switching result to the cabinet management module through a CAN communication interface of the BMC module;
and the cabinet management module is used for realizing communication between the host and the standby machine.
With reference to fig. 2, the home-made Loongson computer platform initializes the work flow for the dual-redundancy computer:
the basic initialization workflow of the dual redundant computer hot standby system. After the module is powered on, the BMC module is started, then the GPIO slot position signal is read, if the module is identified as a host machine, the CPU is powered on and started, and if the module is identified as a standby machine, the CPU is delayed to be powered on and started. The CPU initializes and performs self-checking, and then sends the related information of the self-checking to the on-board BMC health management board through RS 232. If the running state is abnormal, the BMC module in the board sends fault warning information; if the running state is normal, the module enters a normal working state. The initialization exception handling is shown in table 1 below:
TABLE 1 System initialization exception handling
Note: assume host a is the default host and host B is the default standby (identified by the slot signal).
Further, in one embodiment, the dual-redundancy computer device further includes a monitoring module, configured to suspend the dual-redundancy computer device when receiving the failure warning signal, or switch a normal operation mode of the dual-redundancy computer device to a stand-alone operation mode when there is one computer device in the main or standby computer that operates normally; the normal working mode is that the main machine and the standby machine work normally, and the single machine working mode is that the main machine or the standby machine which has a fault does not work;
and the fault warning signal is sent to the monitoring module through the RS232 serial port when the BMC module receives the CPU self-checking information that the running state is abnormal.
Further, in one embodiment, the dual redundant computer device further comprises a VGA and an ethernet communication interface. The VGA is used for outputting the state of the computer equipment, and the Ethernet interface is used for updating, upgrading and debugging the computer equipment.
Further, in one embodiment, the status information includes: the ready state indicates whether the current running state of the computer equipment is normal or not, the high level indicates normal, and the low level indicates abnormal; the main/standby state indicates that the current computer equipment is used as a host or a standby computer, the main state is high level, and the standby state is low level; and resetting the board-to-board signal to indicate whether the current computer equipment is to reset and restart the other computer equipment when the other computer equipment fails.
Further, in one embodiment, the manner of switching between the main and standby devices by the main and standby switching module includes:
the heartbeat detection mechanism is as follows: the method comprises the following steps that a host machine and a standby machine mutually monitor heartbeat signals of the other side, when the standby machine is in a ready state, a standby state and normal heartbeat signals (periodic heartbeat signals) and the standby machine does not monitor the heartbeat signals of the host machine in a plurality of periods and sends an appointed command to the host machine to be not responded (indicating that the host machine fails), the standby machine sends a main-standby switching request signal to a main-standby switching module, the main-standby switching module realizes the switching of the main machine, the main state of the current host machine is converted into a standby state (the output signal of the main state is pulled down), and the standby state of the current standby machine is converted into a main state (the output signal of the standby state is pulled up;
a handover command mechanism: the host sends a main/standby switching command to the main/standby switching module, the main/standby switching module switches the main/standby state of the host into a standby state, and the standby state of the standby host is switched into the main state.
Further, in one embodiment, the master/slave switching request signal/master/slave switching command is sent through a GPIO.
Here, the master/slave switching request signal/master/slave switching command is generally carried by a certain bit of data in a byte corresponding to the heartbeat signal, for example, one byte: the 0 th bit is defined as a bit signal, and the 1 st bit is defined as a switching request signal.
Further, in one embodiment, the heartbeat signal is sent between the host computer and the standby computer through an RS232 serial port.
Further, in one embodiment, the standby machine sends the provisioning command to the host machine, specifically, the provisioning command is sent through the cabinet management module.
Based on the above embodiment, with reference to fig. 3, when the dual-redundancy hot standby initialization is completed, the system may enter the dual-redundancy hot standby operating state. This working state involves two types of working scenarios:
scenario 1: host computer self-checking fault and actively sending switching request
The host finds self-failure in the self-checking process, detects that the standby machine is in a ready state and the standby machine has normal heartbeat, and sends a switching request signal to the standby machine through the serial port and sets the current main state signal to be a low level. The standby machine receives the state signal and the switching request signal of the host through the serial port, and prepares for the standby machine to take over the system when the standby machine recognizes that the main state signal is set to be low level. And the system application layer combines the latest synchronous data to calculate and process the received system data, and the hot standby management component switches the host machine and the standby machine. The state signal of the standby machine is set to be high level, and the standby machine informs the taken-over host machine through the serial port, and at the moment, the standby machine takes over the system. After the host machine recognizes that the standby machine completes the switching between the host machine and the standby machine, the information is broadcasted to other modules, the information is reported to the cabinet management module through the CAN interface of the BMC module, and then the standby machine determines whether to reset and restart the host machine according to the preset information.
Scenario 2: the host is out of control or halted, and the standby machine is actively switched
When the standby machine cannot receive the serial heartbeat signal of the host machine and the appointed signal actively sent by the standby machine is not replied, the standby machine considers that the host machine is out of control and needs to actively take over the system. Meanwhile, in order to prevent misjudgment, the cabinet management module inquires whether the host is normal or not, and if the host does not respond, the system can judge that the host is out of control. At this time, the standby machine can combine the latest synchronous data of the system application layer to analyze and process the received system data, and simultaneously switch the host machine and the standby machine for the system. The standby machine sets the main state signal to be high level, starts to send data outwards and broadcasts the data to other modules. The standby machine reports to the cabinet management module through the CAN interface of the BMC module, and then the standby machine determines whether to reset and restart the host according to system presetting.
Further, in one embodiment, the active/standby synchronization module specifically uses an FC-AE-1553 communication card to synchronize data and state information of the host and the standby.
Further, in one embodiment, the domestic loongson platform adopts a loongson 2K1000 chip; the BMC module adopts HHD32F 103.
The utility model discloses in all signal transmission, differentiate, control etc. all have hardware and hardware interface to realize, not relate to the software program.
The utility model provides a dual-redundancy computer equipment of domestic godson platform has not only accomplished autonomic controllable, has still improved computer system's fault-tolerant ability and reliability greatly to expanded domestic computer's application scene, satisfied domestic most computer system's application demand completely.
The foregoing illustrates and describes the principles, general features, and advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the above embodiments, and that the foregoing embodiments and descriptions are provided only to illustrate the principles of the present invention without departing from the spirit and scope of the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. A dual-redundancy computer device based on a domestic Loongson platform is characterized by comprising a main computer device and a standby computer device which are respectively marked as a main computer and a standby computer and are deployed on the domestic Loongson platform, a main and standby synchronization module, a main and standby switching module and a cabinet management module; each computer device includes: a BMC module and a measurement and control CPU module; the BMC module is provided with a CAN and GPIO communication interface;
the BMC module is used for reading slot position information of the GPIO communication interface, identifying a host and a standby machine according to the information, controlling the corresponding measurement and control CPU module to be immediately powered on and started and perform self-checking on the host, and controlling the corresponding measurement and control CPU module to delay the powering on and started and perform self-checking on the standby machine; the BMC module is used for receiving the CPU self-checking information and controlling the CPU module to normally work when the CPU self-checking information is in a normal running state;
the main and standby synchronization module is used for synchronizing data and state information of the main machine and the standby machine in real time;
the main/standby switching module is used for monitoring heartbeat signals and switching command signals of the host and the standby machines in real time, switching the main/standby machines according to the heartbeat signals and the switching command signals, broadcasting a switching result to other modules, and reporting the switching result to the cabinet management module through a CAN communication interface of the BMC module;
and the cabinet management module is used for realizing communication between the host and the standby machine.
2. The dual-redundancy computer device based on the domestic Loongson platform as claimed in claim 1, further comprising a monitoring module for suspending the dual-redundancy computer device from operating when a fault warning signal is received, or switching the normal operating mode of the dual-redundancy computer device to a stand-alone operating mode when there is one computer device in the main or standby computer to operate normally; the normal working mode is that the main machine and the standby machine work normally, and the single machine working mode is that the main machine or the standby machine which has a fault does not work;
and the fault warning signal is sent to the monitoring module through the RS232 serial port when the BMC module receives the CPU self-checking information that the running state is abnormal.
3. The dual redundant computer device based on a domestic Loongson platform of claim 1, further comprising a VGA for outputting the status of the computer device and an Ethernet communication interface for updating, upgrading and debugging the computer device.
4. The dual redundant computer device based on a domestic loongson platform according to claim 1, wherein said state information comprises: the ready state indicates whether the current running state of the computer equipment is normal or not, the high level indicates normal, and the low level indicates abnormal; the main/standby state indicates that the current computer equipment is used as a host or a standby computer, the main state is high level, and the standby state is low level; and resetting the board-to-board signal to indicate whether the current computer equipment is to reset and restart the other computer equipment when the other computer equipment fails.
5. The dual-redundancy computer device based on the domestic Loongson platform according to claim 1 or 4, wherein the manner of switching between the main and standby switching modules includes:
the heartbeat detection mechanism is as follows: the method comprises the steps that a host machine and a standby machine mutually monitor heartbeat signals of the other side, when the standby machine is in a ready state, a standby state and normal heartbeat signals, and the standby machine does not monitor the heartbeat signals of the host machine in a plurality of periods, and when the standby machine does not respond when sending an appointed command to the host machine, the standby machine sends a standby and standby switching request signal to a standby and standby switching module, the standby and standby switching module realizes the switching of the standby and standby machines, the main state of the current host machine is converted into the standby state, and the standby state of the current standby machine is converted into the main state;
a handover command mechanism: the host machine sends a main-standby switching command to the main-standby switching module, the main-standby switching module realizes the main-standby switching, the main state of the current host machine is converted into a standby state, and the standby state of the current standby machine is converted into the main state.
6. The dual-redundancy computer device based on the domestic Loongson platform of claim 5, wherein the master/slave switching request signal/master/slave switching command is sent through a GPIO.
7. The dual-redundancy computer device based on the domestic Loongson platform as claimed in claim 5, wherein the heartbeat signal is sent between the host computer and the standby computer through an RS232 serial port.
8. The dual-redundancy computer device based on the domestic Loongson platform of claim 5, wherein the standby machine sends the contract command to the host machine, and specifically sends the contract command through the cabinet management module.
9. The dual-redundancy computer device based on the domestic Loongson platform of claim 1, wherein the active and standby synchronization modules specifically utilize an FC-AE-1553 communication card to realize synchronization of host and standby data and state information.
10. The dual-redundancy computer device based on the domestic Loongson platform of claim 1, wherein the domestic Loongson platform adopts a Loongson 2K1000 chip; the BMC module adopts HHD32F 103.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202021358740.XU CN212541329U (en) | 2020-07-10 | 2020-07-10 | Dual-redundancy computer equipment based on domestic Loongson platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202021358740.XU CN212541329U (en) | 2020-07-10 | 2020-07-10 | Dual-redundancy computer equipment based on domestic Loongson platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN212541329U true CN212541329U (en) | 2021-02-12 |
Family
ID=74521829
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202021358740.XU Active CN212541329U (en) | 2020-07-10 | 2020-07-10 | Dual-redundancy computer equipment based on domestic Loongson platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN212541329U (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113176982A (en) * | 2021-05-28 | 2021-07-27 | 西安超越申泰信息科技有限公司 | Device and method for realizing VPX architecture-based chassis management system |
| CN114116279A (en) * | 2021-11-08 | 2022-03-01 | 陕西千山航空电子有限责任公司 | Electromechanical management system |
-
2020
- 2020-07-10 CN CN202021358740.XU patent/CN212541329U/en active Active
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113176982A (en) * | 2021-05-28 | 2021-07-27 | 西安超越申泰信息科技有限公司 | Device and method for realizing VPX architecture-based chassis management system |
| CN114116279A (en) * | 2021-11-08 | 2022-03-01 | 陕西千山航空电子有限责任公司 | Electromechanical management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111767244A (en) | Dual-redundancy computer equipment based on domestic Loongson platform | |
| CN104050061B (en) | A kind of Based PC Ie bus many master control board redundancies standby system | |
| CN103425553B (en) | Duplicated hot-standby system and method for detecting faults of duplicated hot-standby system | |
| CN110427283B (en) | Dual-redundancy fuel management computer system | |
| US8990632B2 (en) | System for monitoring state information in a multiplex system | |
| US11573737B2 (en) | Method and apparatus for performing disk management of all flash array server | |
| CN212541329U (en) | Dual-redundancy computer equipment based on domestic Loongson platform | |
| CN102662803A (en) | Double-controlled double-active redundancy equipment | |
| US9424220B2 (en) | Method and apparatus for setting working mode of multi-processor system | |
| CN102354261A (en) | Remote control system for power supply switches of machine room servers | |
| CN110985426B (en) | Fan control system and method for PCIE Switch product | |
| CN105549696A (en) | Rack-mounted server system with case management function | |
| US6943463B2 (en) | System and method of testing connectivity between a main power supply and a standby power supply | |
| CN204406385U (en) | The management devices of computer system | |
| CN111984471B (en) | Cabinet power BMC redundancy management system and method | |
| JP2008152552A (en) | Computer system and failure information management method | |
| CN110740066A (en) | Cross-machine fault migration method and system with unchangeable seats of types | |
| WO2022267341A1 (en) | Data processing apparatus and method, and computer device and storage medium | |
| TW201201013A (en) | Method and multiple computer system with a failover support to manage shared resources | |
| CN111880999B (en) | High-availability monitoring management device for high-density blade server and redundancy switching method | |
| CN113535471A (en) | Cluster server | |
| CN103532728A (en) | Method and device for resetting fault digital signal processor (DSP) chip | |
| CN107885621B (en) | Hot standby computer based on Feiteng platform | |
| JP2021120827A (en) | Control system and control method | |
| US9639438B2 (en) | Methods and systems of managing an interconnection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 222001 No.18 Shenghu Road, Lianyungang City, Jiangsu Province Patentee after: The 716th Research Institute of China Shipbuilding Corp. Address before: 222001 No.18 Shenghu Road, Lianyungang City, Jiangsu Province Patentee before: 716TH RESEARCH INSTITUTE OF CHINA SHIPBUILDING INDUSTRY Corp. |
|
| CP01 | Change in the name or title of a patent holder |